© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5086
    Prev
    Next
    INDEX
    Explanations

    words within mathematical formulas, theoretical physics and hockey teams and leagues

    oai_token-act-pair · gemini-2.0-flash

    math terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StackNavigator
    -0.57
     مواليد
    -0.56
    concel
    -0.55
     насељу
    -0.54
    
    -0.54
     Dacia
    -0.50
    achau
    -0.49
     DbSet
    -0.49
     msglen
    -0.48
     Sopho
    -0.47
    POSITIVE LOGITS
     real
    0.59
     Re
    0.58
     Cohn
    0.57
    είς
    0.54
    PASO
    0.51
     detik
    0.49
     complex
    0.49
    Re
    0.49
    HandlerContext
    0.49
    real
    0.47
    Activations Density 3.837%

    No Known Activations